Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.7478. Min Act: -0.1700
Data Index: 6629121 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.6853. Min Act: -0.1700
Data Index: 6132143 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.3728. Min Act: -0.1700
Data Index: 2847979 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.3103. Min Act: -0.1700
Data Index: 3004651 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.2478. Min Act: -0.1700
Data Index: 6298840 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.2165. Min Act: -0.1700
Data Index: 8296837 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.0915. Min Act: -0.1700
Data Index: 8069358 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.0603. Min Act: -0.1700
Data Index: 848426 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.0603. Min Act: -0.1700
Data Index: 1160962 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.0603. Min Act: -0.1700
Data Index: 1207361 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.0915. Min Act: -0.1700
Data Index: 3212098 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9978. Min Act: -0.1700
Data Index: 6943403 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9978. Min Act: -0.1700
Data Index: 5492265 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9978. Min Act: -0.1700
Data Index: 7383157 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9665. Min Act: -0.1700
Data Index: 6239495 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9665. Min Act: -0.1700
Data Index: 2871940 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9978. Min Act: -0.1700
Data Index: 593671 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9353. Min Act: -0.1700
Data Index: 3089785 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9040. Min Act: -0.1700
Data Index: 7199162 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7478. Min Range: -6.7478
Max Act: 5.9040. Min Act: -0.1700
Data Index: 5013614 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19